AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

TopoSRL: Topology preserving self-supervised Simplicial Representation Learning

Hiren Madhu, Sundeep Prabhakar Chepuri

NeurIPS 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use proposed augmentation (add open, remove closed simplices) instead of random augmentation (ablation)TopoSRL · contact-high-school order 3accuracy: 0.62 -> 0.92Improved
use proposed augmentation instead of random (ablation)TopoSRL · contact-primary-school order 3accuracy: 0.36 -> 0.61Improved
use proposed augmentation instead of random (ablation)TopoSRL · senate-bills order 3accuracy: 0.52 -> 0.72Improved
also remove closed simplices instead of only adding open simplices (ablation)TopoSRL · contact-high-school order 3accuracy: 0.81 -> 0.92Improved
also remove closed simplices instead of only adding open simplices (ablation)TopoSRL · contact-primary-school order 3accuracy: 0.51 -> 0.61Improved
only add open simplices instead of random augmentation (ablation)TopoSRL · contact-high-school order 3accuracy: 0.62 -> 0.81Improved
include simplices of order 4 instead of order 3 only (ablation)TopoSRL · contact-high-schoolaccuracy: 0.92 -> 0.85Hurt
include simplices of order 4 instead of order 3 only (ablation)TopoSRL · contact-primary-schoolaccuracy: 0.61 -> 0.52Hurt
use TopoSRL (SSL) instead of supervised MPSN with 20% train labelsMPSN · contact-high-schoolaccuracy: 0.74 -> 0.79Improved
use TopoSRL instead of supervised MPSN with 40% train labelsMPSN · contact-high-schoolaccuracy: 0.80 -> 0.84Improved
increase training split from 20% to 80%TopoSRL · contact-high-schoolaccuracy: 0.79 -> 0.92Improved
use TopoSRL instead of MPSNMPSN · contact-primary-school node classificationaccuracy: 0.79 ± 0.06 -> 0.61 ± 0.05Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy